# Writing

Long-form articles on LLM agent systems, infrastructure, and security.

## Engineering a Hardened AI Agent Node

2026-03-30

A step-by-step guide to running an AI agent on a rented server with zero-trust security: key-only SSH, Tailscale private networking, systemd sandboxing, and automatic patching.

[Read article](https://jpmaia.dev/ideas/engineering-a-hardened-ai-agent-node)